© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19841
    Prev
    Next
    INDEX
    Explanations

    Japanese phrases and 'z' words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    嘭
    0.46
    的说
    0.44
    把它
    0.42
     tổn
    0.42
     опять
    0.42
     జమ
    0.42
     ಮತ್ತೆ
    0.42
    之为
    0.41
    ):(
    0.41
     този
    0.41
    POSITIVE LOGITS
    mo
    0.54
    mn
    0.54
    ke
    0.54
    ca
    0.51
    mi
    0.50
    観光
    0.50
    py
    0.50
    mektedir
    0.48
    na
    0.48
    me
    0.47
    Activations Density 0.002%

    No Known Activations